148 lines
4.0 KiB
Python
148 lines
4.0 KiB
Python
import datetime
|
|
import inspect
|
|
import logging
|
|
from collections.abc import Sequence
|
|
from pathlib import Path
|
|
|
|
import requests
|
|
import requests_cache
|
|
|
|
from . import data, fetchers, notification, util
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
try:
|
|
import cfscrape
|
|
except ImportError:
|
|
cfscrape = None
|
|
logger.warning('cfscrape not installed: Certain fetchers might not work')
|
|
|
|
try:
|
|
import browsercookie
|
|
except ImportError:
|
|
logger.warning('browsercookie not installed: Certain fetchers might not work')
|
|
browsercookie = None
|
|
|
|
|
|
OUTPUT_PATH = Path('./output')
|
|
|
|
logging.basicConfig()
|
|
logger.setLevel('INFO')
|
|
|
|
|
|
STANDARD_HEADERS = {
|
|
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:122.0) Gecko/20100101 Firefox/122.0',
|
|
'Accept-Language': 'en-US,en;q=0.5',
|
|
'Accept-Encoding': 'gzip, deflate, br',
|
|
}
|
|
|
|
|
|
if cfscrape:
|
|
|
|
class CachedCfScrape(requests_cache.CacheMixin, cfscrape.CloudflareScraper):
|
|
pass
|
|
|
|
|
|
CACHE_EXPIRE_DEFAULT = datetime.timedelta(days=7)
|
|
|
|
|
|
def get_session(
|
|
cookiejar: Sequence,
|
|
*,
|
|
with_cfscrape: bool,
|
|
ignore_cache: bool,
|
|
) -> requests.Session:
|
|
if with_cfscrape and cfscrape:
|
|
session_class = CachedCfScrape
|
|
if ignore_cache:
|
|
logger.warning('HTTP cache disabled')
|
|
return cfscrape.create_scraper()
|
|
else:
|
|
session_class = requests_cache.CachedSession
|
|
if ignore_cache:
|
|
logger.warning('HTTP cache disabled')
|
|
return requests.Session()
|
|
session = session_class(
|
|
OUTPUT_PATH / 'web_cache',
|
|
cookies=cookiejar,
|
|
expire_after=CACHE_EXPIRE_DEFAULT,
|
|
)
|
|
for cookie in cookiejar:
|
|
session.cookies.set_cookie(cookie)
|
|
return session
|
|
|
|
|
|
def available_scrapers() -> list[type[data.Scraper]]:
|
|
fetchers.load_fetcher_modules()
|
|
subclasses = []
|
|
class_queue = [data.Scraper]
|
|
while class_queue:
|
|
clazz = class_queue.pop()
|
|
if inspect.isabstract(clazz):
|
|
class_queue.extend(clazz.__subclasses__())
|
|
else:
|
|
subclasses.append(clazz)
|
|
return subclasses
|
|
|
|
|
|
def available_scraper_names() -> list[str]:
|
|
return [scraper_cls.__name__ for scraper_cls in available_scrapers()]
|
|
|
|
|
|
def main(
|
|
scraper_filter: frozenset[str],
|
|
*,
|
|
use_cookiejar: bool,
|
|
ignore_cache: bool,
|
|
notification_types: frozenset[notification.NotificationType],
|
|
) -> None:
|
|
if use_cookiejar:
|
|
cookiejar = browsercookie.firefox()
|
|
logger.info('Got cookiejar from firefox: %s cookies', len(cookiejar))
|
|
else:
|
|
cookiejar = []
|
|
logger.warning('No cookiejar is used')
|
|
|
|
if len(notification_types) == 0:
|
|
logger.info('No notifications enabled: Notifications will not be sent!')
|
|
|
|
for scraper_cls in available_scrapers():
|
|
session = get_session(
|
|
cookiejar,
|
|
with_cfscrape=scraper_cls.requires_cfscrape(),
|
|
ignore_cache=ignore_cache,
|
|
)
|
|
scraper = scraper_cls(session)
|
|
if scraper_cls.__name__ not in scraper_filter:
|
|
continue
|
|
logger.info(
|
|
'Running %s, appending to "%s"',
|
|
scraper_cls.__name__,
|
|
scraper.dataset_name,
|
|
)
|
|
result_rows = []
|
|
try:
|
|
for result in scraper.scrape():
|
|
result_rows.append(result)
|
|
del result
|
|
except requests.exceptions.HTTPError:
|
|
logger.exception('Failed in running %s', scraper_cls.__name__)
|
|
continue
|
|
status = util.extend_csv_file(
|
|
OUTPUT_PATH / f'{scraper.dataset_name}.csv',
|
|
result_rows,
|
|
deduplicate_mode=scraper.deduplicate_mode,
|
|
deduplicate_ignore_columns=scraper.deduplicate_ignore_columns(),
|
|
)
|
|
logger.info('Scraper done: %s', scraper.dataset_name)
|
|
|
|
if status['extended']:
|
|
notification.send_notifications(
|
|
session,
|
|
scraper_cls.__name__,
|
|
status['dicts'][-1],
|
|
notification_types,
|
|
)
|
|
|
|
del scraper, session
|